xinyin025/one-api
1
0
Fork 0
mirror of https://github.com/songquanpeng/one-api.git synced 2025-09-19 01:56:37 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

feat: update model list and add new model ratios for billing calculations

Browse Source
This commit is contained in:
Laisky.Cai 2025-03-16 12:50:06 +00:00
parent 3bf121aae8
commit 4bdc2835bd
2 changed files with 28 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
relay/adaptor/groq/constants.go
View File

@ -1,27 +1,32 @@
package groq
// ModelList is a list of models that can be used with Groq.
//
// https://console.groq.com/docs/models
var ModelList = []string{
// Regular Models
"distil-whisper-large-v3-en",
"gemma2-9b-it",
"llama-3.1-70b-versatile",
"llama-3.3-70b-versatile",
"llama-3.1-8b-instant",
"llama-3.2-11b-text-preview",
"llama-3.2-11b-vision-preview",
"llama-3.2-1b-preview",
"llama-3.2-3b-preview",
"llama-3.2-90b-text-preview",
"llama-3.2-90b-vision-preview",
"llama-guard-3-8b",
"llama3-70b-8192",
"llama3-8b-8192",
"llama3-groq-70b-8192-tool-use-preview",
"llama3-groq-8b-8192-tool-use-preview",
"llava-v1.5-7b-4096-preview",
"mixtral-8x7b-32768",
"distil-whisper-large-v3-en",
"whisper-large-v3",
"whisper-large-v3-turbo",
// Preview Models
"qwen-qwq-32b",
"mistral-saba-24b",
"qwen-2.5-coder-32b",
"qwen-2.5-32b",
"deepseek-r1-distill-qwen-32b",
"deepseek-r1-distill-llama-70b-specdec",
"deepseek-r1-distill-llama-70b",
"llama-3.2-1b-preview",
"llama-3.2-3b-preview",
"llama-3.2-11b-vision-preview",
"llama-3.2-90b-vision-preview",
"llama-3.3-70b-specdec",
}

12
relay/billing/ratio/model.go
View File

@ -341,6 +341,11 @@ var ModelRatio = map[string]float64{
"llama3-8b-8192": 0.05 * MilliTokensUsd,
"llama3-groq-70b-8192-tool-use-preview": 0.59 * MilliTokensUsd,
"llama3-groq-8b-8192-tool-use-preview": 0.05 * MilliTokensUsd,
"llama-3.3-70b-specdec": 0.59 * MilliTokensUsd,
"mistral-saba-24b": 0.79 * MilliTokensUsd,
"qwen-qwq-32b": 0.29 * MilliTokensUsd,
"qwen-2.5-coder-32b": 0.79 * MilliTokensUsd,
"qwen-2.5-32b": 0.79 * MilliTokensUsd,
"mixtral-8x7b-32768": 0.24 * MilliTokensUsd,
"whisper-large-v3": 0.111 * MilliTokensUsd,
"whisper-large-v3-turbo": 0.04 * MilliTokensUsd,
@ -717,9 +722,14 @@ var CompletionRatio = map[string]float64{
"llama3-groq-70b-8192-tool-use-preview": 0.79 / 0.59,
"llama3-groq-8b-8192-tool-use-preview": 0.08 / 0.05,
"mixtral-8x7b-32768": 1.0,
"deepseek-r1-distill-qwen-32b": 1,
"deepseek-r1-distill-qwen-32b": 1.0,
"deepseek-r1-distill-llama-70b-specdec": 0.99 / 0.75,
"deepseek-r1-distill-llama-70b": 0.99 / 0.75,
"llama-3.3-70b-specdec": 0.99 / 0.59,
"mistral-saba-24b": 1.0,
"qwen-qwq-32b": 0.39 / 0.29,
"qwen-2.5-coder-32b": 1.0,
"qwen-2.5-32b": 1.0,
// -------------------------------------
// Replicate
// -------------------------------------